github-mirrors/VictoriaMetrics
1
0
Fork 0
mirror of https://github.com/VictoriaMetrics/VictoriaMetrics.git synced 2024-11-21 14:44:00 +00:00
Code Issues Projects Releases Packages Wiki Activity

vmalert: automatically reload configuration on file change (#1326)

Browse source 
New flag `-rule.configCheckInterval` defines how often `vmalert` will re-read
config file. If it detects any changes, the config will be reloaded.
This behaviour is turned off by default.

https://github.com/VictoriaMetrics/VictoriaMetrics/issues/512
This commit is contained in:
Roman Khavronenko 2021-05-25 14:27:22 +01:00 committed by Aliaksandr Valialkin
parent 6b90570ed3
commit e183a5c532
6 changed files with 300 additions and 145 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
app/vmalert/Makefile
View file

@ -66,7 +66,8 @@ run-vmalert: vmalert
-remoteRead.url=http://localhost:8428 \ -remoteRead.url=http://localhost:8428 \
-external.label=cluster=east-1 \ -external.label=cluster=east-1 \
-external.label=replica=a \ -external.label=replica=a \
-evaluationInterval=3s -evaluationInterval=3s \
-rule.configCheckInterval=10s
vmalert-amd64: vmalert-amd64:
CGO_ENABLED=1 GOARCH=amd64 $(MAKE) vmalert-local-with-goarch CGO_ENABLED=1 GOARCH=amd64 $(MAKE) vmalert-local-with-goarch

203
app/vmalert/README.md
View file

@ -233,188 +233,193 @@ to set `-datasource.appendTypePrefix` flag to `true`, so vmalert can adjust URL
The shortlist of configuration flags is the following: The shortlist of configuration flags is the following:
``` ```
-datasource.appendTypePrefix -datasource.appendTypePrefix
Whether to add type prefix to -datasource.url based on the query type. Set to true if sending different query types to the vmselect URL. Whether to add type prefix to -datasource.url based on the query type. Set to true if sending different query types to the vmselect URL.
-datasource.basicAuth.password string -datasource.basicAuth.password string
Optional basic auth password for -datasource.url Optional basic auth password for -datasource.url
-datasource.basicAuth.username string -datasource.basicAuth.username string
Optional basic auth username for -datasource.url Optional basic auth username for -datasource.url
-datasource.lookback duration -datasource.lookback duration
Lookback defines how far into the past to look when evaluating queries. For example, if the datasource.lookback=5m then param "time" with value now()-5m will be added to every query. Lookback defines how far into the past to look when evaluating queries. For example, if the datasource.lookback=5m then param "time" with value now()-5m will be added to every query.
-datasource.maxIdleConnections int -datasource.maxIdleConnections int
Defines the number of idle (keep-alive connections) to each configured datasource. Consider setting this value equal to the value: groups_total * group.concurrency. Too low a value may result in a high number of sockets in TIME_WAIT state. (default 100) Defines the number of idle (keep-alive connections) to each configured datasource. Consider setting this value equal to the value: groups_total * group.concurrency. Too low a value may result in a high number of sockets in TIME_WAIT state. (default 100)
-datasource.queryStep duration -datasource.queryStep duration
queryStep defines how far a value can fallback to when evaluating queries. For example, if datasource.queryStep=15s then param "step" with value "15s" will be added to every query.If queryStep isn't specified, rule's evaluationInterval will be used instead. queryStep defines how far a value can fallback to when evaluating queries. For example, if datasource.queryStep=15s then param "step" with value "15s" will be added to every query.If queryStep isn't specified, rule's evaluationInterval will be used instead.
-datasource.roundDigits int -datasource.roundDigits int
Adds "round_digits" GET param to datasource requests. In VM "round_digits" limits the number of digits after the decimal point in response values. Adds "round_digits" GET param to datasource requests. In VM "round_digits" limits the number of digits after the decimal point in response values.
-datasource.tlsCAFile string -datasource.tlsCAFile string
Optional path to TLS CA file to use for verifying connections to -datasource.url. By default, system CA is used Optional path to TLS CA file to use for verifying connections to -datasource.url. By default, system CA is used
-datasource.tlsCertFile string -datasource.tlsCertFile string
Optional path to client-side TLS certificate file to use when connecting to -datasource.url Optional path to client-side TLS certificate file to use when connecting to -datasource.url
-datasource.tlsInsecureSkipVerify -datasource.tlsInsecureSkipVerify
Whether to skip tls verification when connecting to -datasource.url Whether to skip tls verification when connecting to -datasource.url
-datasource.tlsKeyFile string -datasource.tlsKeyFile string
Optional path to client-side TLS certificate key to use when connecting to -datasource.url Optional path to client-side TLS certificate key to use when connecting to -datasource.url
-datasource.tlsServerName string -datasource.tlsServerName string
Optional TLS server name to use for connections to -datasource.url. By default, the server name from -datasource.url is used Optional TLS server name to use for connections to -datasource.url. By default, the server name from -datasource.url is used
-datasource.url string -datasource.url string
VictoriaMetrics or vmselect url. Required parameter. E.g. http://127.0.0.1:8428 VictoriaMetrics or vmselect url. Required parameter. E.g. http://127.0.0.1:8428
-dryRun -rule -dryRun -rule
Whether to check only config files without running vmalert. The rules file are validated. The -rule flag must be specified. Whether to check only config files without running vmalert. The rules file are validated. The -rule flag must be specified.
-enableTCP6 -enableTCP6
Whether to enable IPv6 for listening and dialing. By default only IPv4 TCP and UDP is used Whether to enable IPv6 for listening and dialing. By default only IPv4 TCP and UDP is used
-envflag.enable -envflag.enable
Whether to enable reading flags from environment variables additionally to command line. Command line flag values have priority over values from environment vars. Flags are read only from command line if this flag isn't set Whether to enable reading flags from environment variables additionally to command line. Command line flag values have priority over values from environment vars. Flags are read only from command line if this flag isn't set
-envflag.prefix string -envflag.prefix string
Prefix for environment variables if -envflag.enable is set Prefix for environment variables if -envflag.enable is set
-evaluationInterval duration -evaluationInterval duration
How often to evaluate the rules (default 1m0s) How often to evaluate the rules (default 1m0s)
-external.alert.source string -external.alert.source string
External Alert Source allows to override the Source link for alerts sent to AlertManager for cases where you want to build a custom link to Grafana, Prometheus or any other service. External Alert Source allows to override the Source link for alerts sent to AlertManager for cases where you want to build a custom link to Grafana, Prometheus or any other service.
eg. 'explore?orgId=1&left=[\"now-1h\",\"now\",\"VictoriaMetrics\",{\"expr\": \"{{$expr|quotesEscape|crlfEscape|queryEscape}}\"},{\"mode\":\"Metrics\"},{\"ui\":[true,true,true,\"none\"]}]'.If empty '/api/v1/:groupID/alertID/status' is used eg. 'explore?orgId=1&left=[\"now-1h\",\"now\",\"VictoriaMetrics\",{\"expr\": \"{{$expr|quotesEscape|crlfEscape|queryEscape}}\"},{\"mode\":\"Metrics\"},{\"ui\":[true,true,true,\"none\"]}]'.If empty '/api/v1/:groupID/alertID/status' is used
-external.label array -external.label array
Optional label in the form 'name=value' to add to all generated recording rules and alerts. Pass multiple -label flags in order to add multiple label sets. Optional label in the form 'name=value' to add to all generated recording rules and alerts. Pass multiple -label flags in order to add multiple label sets.
Supports an array of values separated by comma or specified via multiple flags. Supports an array of values separated by comma or specified via multiple flags.
-external.url string -external.url string
External URL is used as alert's source for sent alerts to the notifier External URL is used as alert's source for sent alerts to the notifier
-fs.disableMmap -fs.disableMmap
Whether to use pread() instead of mmap() for reading data files. By default mmap() is used for 64-bit arches and pread() is used for 32-bit arches, since they cannot read data files bigger than 2^32 bytes in memory. mmap() is usually faster for reading small data chunks than pread() Whether to use pread() instead of mmap() for reading data files. By default mmap() is used for 64-bit arches and pread() is used for 32-bit arches, since they cannot read data files bigger than 2^32 bytes in memory. mmap() is usually faster for reading small data chunks than pread()
-http.connTimeout duration -http.connTimeout duration
Incoming http connections are closed after the configured timeout. This may help to spread the incoming load among a cluster of services behind a load balancer. Please note that the real timeout may be bigger by up to 10% as a protection against the thundering herd problem (default 2m0s) Incoming http connections are closed after the configured timeout. This may help to spread the incoming load among a cluster of services behind a load balancer. Please note that the real timeout may be bigger by up to 10% as a protection against the thundering herd problem (default 2m0s)
-http.disableResponseCompression -http.disableResponseCompression
Disable compression of HTTP responses to save CPU resources. By default compression is enabled to save network bandwidth Disable compression of HTTP responses to save CPU resources. By default compression is enabled to save network bandwidth
-http.idleConnTimeout duration -http.idleConnTimeout duration
Timeout for incoming idle http connections (default 1m0s) Timeout for incoming idle http connections (default 1m0s)
-http.maxGracefulShutdownDuration duration -http.maxGracefulShutdownDuration duration
The maximum duration for a graceful shutdown of the HTTP server. A highly loaded server may require increased value for a graceful shutdown (default 7s) The maximum duration for a graceful shutdown of the HTTP server. A highly loaded server may require increased value for a graceful shutdown (default 7s)
-http.pathPrefix string -http.pathPrefix string
An optional prefix to add to all the paths handled by http server. For example, if '-http.pathPrefix=/foo/bar' is set, then all the http requests will be handled on '/foo/bar/*' paths. This may be useful for proxied requests. See https://www.robustperception.io/using-external-urls-and-proxies-with-prometheus An optional prefix to add to all the paths handled by http server. For example, if '-http.pathPrefix=/foo/bar' is set, then all the http requests will be handled on '/foo/bar/*' paths. This may be useful for proxied requests. See https://www.robustperception.io/using-external-urls-and-proxies-with-prometheus
-http.shutdownDelay duration -http.shutdownDelay duration
Optional delay before http server shutdown. During this delay, the server returns non-OK responses from /health page, so load balancers can route new requests to other servers Optional delay before http server shutdown. During this delay, the server returns non-OK responses from /health page, so load balancers can route new requests to other servers
-httpAuth.password string -httpAuth.password string
Password for HTTP Basic Auth. The authentication is disabled if -httpAuth.username is empty Password for HTTP Basic Auth. The authentication is disabled if -httpAuth.username is empty
-httpAuth.username string -httpAuth.username string
Username for HTTP Basic Auth. The authentication is disabled if empty. See also -httpAuth.password Username for HTTP Basic Auth. The authentication is disabled if empty. See also -httpAuth.password
-httpListenAddr string -httpListenAddr string
Address to listen for http connections (default ":8880") Address to listen for http connections (default ":8880")
-loggerDisableTimestamps -loggerDisableTimestamps
Whether to disable writing timestamps in logs Whether to disable writing timestamps in logs
-loggerErrorsPerSecondLimit int -loggerErrorsPerSecondLimit int
Per-second limit on the number of ERROR messages. If more than the given number of errors are emitted per second, the remaining errors are suppressed. Zero values disable the rate limit Per-second limit on the number of ERROR messages. If more than the given number of errors are emitted per second, the remaining errors are suppressed. Zero values disable the rate limit
-loggerFormat string -loggerFormat string
Format for logs. Possible values: default, json (default "default") Format for logs. Possible values: default, json (default "default")
-loggerLevel string -loggerLevel string
Minimum level of errors to log. Possible values: INFO, WARN, ERROR, FATAL, PANIC (default "INFO") Minimum level of errors to log. Possible values: INFO, WARN, ERROR, FATAL, PANIC (default "INFO")
-loggerOutput string -loggerOutput string
Output for the logs. Supported values: stderr, stdout (default "stderr") Output for the logs. Supported values: stderr, stdout (default "stderr")
-loggerTimezone string -loggerTimezone string
Timezone to use for timestamps in logs. Timezone must be a valid IANA Time Zone. For example: America/New_York, Europe/Berlin, Etc/GMT+3 or Local (default "UTC") Timezone to use for timestamps in logs. Timezone must be a valid IANA Time Zone. For example: America/New_York, Europe/Berlin, Etc/GMT+3 or Local (default "UTC")
-loggerWarnsPerSecondLimit int -loggerWarnsPerSecondLimit int
Per-second limit on the number of WARN messages. If more than the given number of warns are emitted per second, then the remaining warns are suppressed. Zero values disable the rate limit Per-second limit on the number of WARN messages. If more than the given number of warns are emitted per second, then the remaining warns are suppressed. Zero values disable the rate limit
-memory.allowedBytes size -memory.allowedBytes size
Allowed size of system memory VictoriaMetrics caches may occupy. This option overrides -memory.allowedPercent if set to a non-zero value. Too low a value may increase the cache miss rate usually resulting in higher CPU and disk IO usage. Too high a value may evict too much data from OS page cache resulting in higher disk IO usage Allowed size of system memory VictoriaMetrics caches may occupy. This option overrides -memory.allowedPercent if set to a non-zero value. Too low a value may increase the cache miss rate usually resulting in higher CPU and disk IO usage. Too high a value may evict too much data from OS page cache resulting in higher disk IO usage
Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 0) Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 0)
-memory.allowedPercent float -memory.allowedPercent float
Allowed percent of system memory VictoriaMetrics caches may occupy. See also -memory.allowedBytes. Too low a value may increase cache miss rate usually resulting in higher CPU and disk IO usage. Too high a value may evict too much data from OS page cache which will result in higher disk IO usage (default 60) Allowed percent of system memory VictoriaMetrics caches may occupy. See also -memory.allowedBytes. Too low a value may increase cache miss rate usually resulting in higher CPU and disk IO usage. Too high a value may evict too much data from OS page cache which will result in higher disk IO usage (default 60)
-metricsAuthKey string -metricsAuthKey string
Auth key for /metrics. It overrides httpAuth settings Auth key for /metrics. It overrides httpAuth settings
-notifier.basicAuth.password array -notifier.basicAuth.password array
Optional basic auth password for -notifier.url Optional basic auth password for -notifier.url
Supports an array of values separated by comma or specified via multiple flags. Supports an array of values separated by comma or specified via multiple flags.
-notifier.basicAuth.username array -notifier.basicAuth.username array
Optional basic auth username for -notifier.url Optional basic auth username for -notifier.url
Supports an array of values separated by comma or specified via multiple flags. Supports an array of values separated by comma or specified via multiple flags.
-notifier.tlsCAFile array -notifier.tlsCAFile array
Optional path to TLS CA file to use for verifying connections to -notifier.url. By default system CA is used Optional path to TLS CA file to use for verifying connections to -notifier.url. By default system CA is used
Supports an array of values separated by comma or specified via multiple flags. Supports an array of values separated by comma or specified via multiple flags.
-notifier.tlsCertFile array -notifier.tlsCertFile array
Optional path to client-side TLS certificate file to use when connecting to -notifier.url Optional path to client-side TLS certificate file to use when connecting to -notifier.url
Supports an array of values separated by comma or specified via multiple flags. Supports an array of values separated by comma or specified via multiple flags.
-notifier.tlsInsecureSkipVerify array -notifier.tlsInsecureSkipVerify array
Whether to skip tls verification when connecting to -notifier.url Whether to skip tls verification when connecting to -notifier.url
Supports array of values separated by comma or specified via multiple flags. Supports array of values separated by comma or specified via multiple flags.
-notifier.tlsKeyFile array -notifier.tlsKeyFile array
Optional path to client-side TLS certificate key to use when connecting to -notifier.url Optional path to client-side TLS certificate key to use when connecting to -notifier.url
Supports an array of values separated by comma or specified via multiple flags. Supports an array of values separated by comma or specified via multiple flags.
-notifier.tlsServerName array -notifier.tlsServerName array
Optional TLS server name to use for connections to -notifier.url. By default the server name from -notifier.url is used Optional TLS server name to use for connections to -notifier.url. By default the server name from -notifier.url is used
Supports an array of values separated by comma or specified via multiple flags. Supports an array of values separated by comma or specified via multiple flags.
-notifier.url array -notifier.url array
Prometheus alertmanager URL. Required parameter. e.g. http://127.0.0.1:9093 Prometheus alertmanager URL. Required parameter. e.g. http://127.0.0.1:9093
Supports an array of values separated by comma or specified via multiple flags. Supports an array of values separated by comma or specified via multiple flags.
-pprofAuthKey string -pprofAuthKey string
Auth key for /debug/pprof. It overrides httpAuth settings Auth key for /debug/pprof. It overrides httpAuth settings
-remoteRead.basicAuth.password string -remoteRead.basicAuth.password string
Optional basic auth password for -remoteRead.url Optional basic auth password for -remoteRead.url
-remoteRead.basicAuth.username string -remoteRead.basicAuth.username string
Optional basic auth username for -remoteRead.url Optional basic auth username for -remoteRead.url
-remoteRead.ignoreRestoreErrors -remoteRead.ignoreRestoreErrors
Whether to ignore errors from remote storage when restoring alerts state on startup. (default true) Whether to ignore errors from remote storage when restoring alerts state on startup. (default true)
-remoteRead.lookback duration -remoteRead.lookback duration
Lookback defines how far to look into past for alerts timeseries. For example, if lookback=1h then range from now() to now()-1h will be scanned. (default 1h0m0s) Lookback defines how far to look into past for alerts timeseries. For example, if lookback=1h then range from now() to now()-1h will be scanned. (default 1h0m0s)
-remoteRead.tlsCAFile string -remoteRead.tlsCAFile string
Optional path to TLS CA file to use for verifying connections to -remoteRead.url. By default system CA is used Optional path to TLS CA file to use for verifying connections to -remoteRead.url. By default system CA is used
-remoteRead.tlsCertFile string -remoteRead.tlsCertFile string
Optional path to client-side TLS certificate file to use when connecting to -remoteRead.url Optional path to client-side TLS certificate file to use when connecting to -remoteRead.url
-remoteRead.tlsInsecureSkipVerify -remoteRead.tlsInsecureSkipVerify
Whether to skip tls verification when connecting to -remoteRead.url Whether to skip tls verification when connecting to -remoteRead.url
-remoteRead.tlsKeyFile string -remoteRead.tlsKeyFile string
Optional path to client-side TLS certificate key to use when connecting to -remoteRead.url Optional path to client-side TLS certificate key to use when connecting to -remoteRead.url
-remoteRead.tlsServerName string -remoteRead.tlsServerName string
Optional TLS server name to use for connections to -remoteRead.url. By default the server name from -remoteRead.url is used Optional TLS server name to use for connections to -remoteRead.url. By default the server name from -remoteRead.url is used
-remoteRead.url vmalert -remoteRead.url vmalert
Optional URL to VictoriaMetrics or vmselect that will be used to restore alerts state. This configuration makes sense only if vmalert was configured with `remoteWrite.url` before and has been successfully persisted its state. E.g. http://127.0.0.1:8428 Optional URL to VictoriaMetrics or vmselect that will be used to restore alerts state. This configuration makes sense only if vmalert was configured with `remoteWrite.url` before and has been successfully persisted its state. E.g. http://127.0.0.1:8428
-remoteWrite.basicAuth.password string -remoteWrite.basicAuth.password string
Optional basic auth password for -remoteWrite.url Optional basic auth password for -remoteWrite.url
-remoteWrite.basicAuth.username string -remoteWrite.basicAuth.username string
Optional basic auth username for -remoteWrite.url Optional basic auth username for -remoteWrite.url
-remoteWrite.concurrency int -remoteWrite.concurrency int
Defines number of writers for concurrent writing into remote querier (default 1) Defines number of writers for concurrent writing into remote querier (default 1)
-remoteWrite.flushInterval duration -remoteWrite.flushInterval duration
Defines interval of flushes to remote write endpoint (default 5s) Defines interval of flushes to remote write endpoint (default 5s)
-remoteWrite.maxBatchSize int -remoteWrite.maxBatchSize int
Defines defines max number of timeseries to be flushed at once (default 1000) Defines defines max number of timeseries to be flushed at once (default 1000)
-remoteWrite.maxQueueSize int -remoteWrite.maxQueueSize int
Defines the max number of pending datapoints to remote write endpoint (default 100000) Defines the max number of pending datapoints to remote write endpoint (default 100000)
-remoteWrite.tlsCAFile string -remoteWrite.tlsCAFile string
Optional path to TLS CA file to use for verifying connections to -remoteWrite.url. By default system CA is used Optional path to TLS CA file to use for verifying connections to -remoteWrite.url. By default system CA is used
-remoteWrite.tlsCertFile string -remoteWrite.tlsCertFile string
Optional path to client-side TLS certificate file to use when connecting to -remoteWrite.url Optional path to client-side TLS certificate file to use when connecting to -remoteWrite.url
-remoteWrite.tlsInsecureSkipVerify -remoteWrite.tlsInsecureSkipVerify
Whether to skip tls verification when connecting to -remoteWrite.url Whether to skip tls verification when connecting to -remoteWrite.url
-remoteWrite.tlsKeyFile string -remoteWrite.tlsKeyFile string
Optional path to client-side TLS certificate key to use when connecting to -remoteWrite.url Optional path to client-side TLS certificate key to use when connecting to -remoteWrite.url
-remoteWrite.tlsServerName string -remoteWrite.tlsServerName string
Optional TLS server name to use for connections to -remoteWrite.url. By default the server name from -remoteWrite.url is used Optional TLS server name to use for connections to -remoteWrite.url. By default the server name from -remoteWrite.url is used
-remoteWrite.url string -remoteWrite.url string
Optional URL to VictoriaMetrics or vminsert where to persist alerts state and recording rules results in form of timeseries. E.g. http://127.0.0.1:8428 Optional URL to VictoriaMetrics or vminsert where to persist alerts state and recording rules results in form of timeseries. E.g. http://127.0.0.1:8428
-rule array -rule array
Path to the file with alert rules. Path to the file with alert rules.
Supports patterns. Flag can be specified multiple times. Supports patterns. Flag can be specified multiple times.
Examples: Examples:
-rule="/path/to/file". Path to a single file with alerting rules -rule="/path/to/file". Path to a single file with alerting rules
-rule="dir/*.yaml" -rule="/*.yaml". Relative path to all .yaml files in "dir" folder, -rule="dir/*.yaml" -rule="/*.yaml". Relative path to all .yaml files in "dir" folder,
absolute path to all .yaml files in root. absolute path to all .yaml files in root.
Rule files may contain %{ENV_VAR} placeholders, which are substituted by the corresponding env vars. Rule files may contain %{ENV_VAR} placeholders, which are substituted by the corresponding env vars.
Supports an array of values separated by comma or specified via multiple flags. Supports an array of values separated by comma or specified via multiple flags.
-rule.configCheckInterval duration
Interval for checking for changes in '-rule' files. By default the checking is disabled. Send SIGHUP signal in order to force config check for changes
-rule.validateExpressions -rule.validateExpressions
Whether to validate rules expressions via MetricsQL engine (default true) Whether to validate rules expressions via MetricsQL engine (default true)
-rule.validateTemplates -rule.validateTemplates
Whether to validate annotation and label templates (default true) Whether to validate annotation and label templates (default true)
-tls -tls
Whether to enable TLS (aka HTTPS) for incoming requests. -tlsCertFile and -tlsKeyFile must be set if -tls is set Whether to enable TLS (aka HTTPS) for incoming requests. -tlsCertFile and -tlsKeyFile must be set if -tls is set
-tlsCertFile string -tlsCertFile string
Path to file with TLS certificate. Used only if -tls is set. Prefer ECDSA certs instead of RSA certs as RSA certs are slower Path to file with TLS certificate. Used only if -tls is set. Prefer ECDSA certs instead of RSA certs as RSA certs are slower
-tlsKeyFile string -tlsKeyFile string
Path to file with TLS key. Used only if -tls is set Path to file with TLS key. Used only if -tls is set
-version -version
Show VictoriaMetrics version Show VictoriaMetrics version
``` ```
Pass `-help` to `vmalert` in order to see the full list of supported Pass `-help` to `vmalert` in order to see the full list of supported
command-line flags with their descriptions. command-line flags with their descriptions.
To reload configuration without `vmalert` restart send SIGHUP signal `vmalert` supports "hot" config reload via the following methods:
or send GET request to `/-/reload` endpoint. * send SIGHUP signal to `vmalert` process;
* send GET request to `/-/reload` endpoint;
* configure `-rule.configCheckInterval` flag for periodic reload
on config change.
## Contributing ## Contributing

93
app/vmalert/main.go
View file

@ -34,6 +34,9 @@ Examples:
absolute path to all .yaml files in root. absolute path to all .yaml files in root.
Rule files may contain %{ENV_VAR} placeholders, which are substituted by the corresponding env vars.`) Rule files may contain %{ENV_VAR} placeholders, which are substituted by the corresponding env vars.`)
rulesCheckInterval = flag.Duration("rule.configCheckInterval", 0, "Interval for checking for changes in '-rule' files. "+
"By default the checking is disabled. Send SIGHUP signal in order to force config check for changes")
httpListenAddr = flag.String("httpListenAddr", ":8880", "Address to listen for http connections") httpListenAddr = flag.String("httpListenAddr", ":8880", "Address to listen for http connections")
evaluationInterval = flag.Duration("evaluationInterval", time.Minute, "How often to evaluate the rules") evaluationInterval = flag.Duration("evaluationInterval", time.Minute, "How often to evaluate the rules")
@ -78,34 +81,17 @@ func main() {
logger.Fatalf("failed to init: %s", err) logger.Fatalf("failed to init: %s", err)
} }
// Register SIGHUP handler for config re-read just before manager.start call. logger.Infof("reading rules configuration file from %q", strings.Join(*rulePath, ";"))
// This guarantees that the config will be re-read if the signal arrives during manager.start call. groupsCfg, err := config.Parse(*rulePath, *validateTemplates, *validateExpressions)
// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1240 if err != nil {
sighupCh := procutil.NewSighupChan() logger.Fatalf("cannot parse configuration file: %s", err)
}
if err := manager.start(ctx, *rulePath, *validateTemplates, *validateExpressions); err != nil { if err := manager.start(ctx, groupsCfg); err != nil {
logger.Fatalf("failed to start: %s", err) logger.Fatalf("failed to start: %s", err)
} }
go func() { go configReload(ctx, manager, groupsCfg)
// init reload metrics with positive values to improve alerting conditions
configSuccess.Set(1)
configTimestamp.Set(fasttime.UnixTimestamp())
for {
<-sighupCh
configReloads.Inc()
logger.Infof("SIGHUP received. Going to reload rules %q ...", *rulePath)
if err := manager.update(ctx, *rulePath, *validateTemplates, *validateExpressions, false); err != nil {
configReloadErrors.Inc()
configSuccess.Set(0)
logger.Errorf("error while reloading rules: %s", err)
continue
}
configSuccess.Set(1)
configTimestamp.Set(fasttime.UnixTimestamp())
logger.Infof("Rules reloaded successfully from %q", *rulePath)
}
}()
rh := &requestHandler{m: manager} rh := &requestHandler{m: manager}
go httpserver.Serve(*httpListenAddr, rh.handler) go httpserver.Serve(*httpListenAddr, rh.handler)
@ -228,3 +214,62 @@ See the docs at https://docs.victoriametrics.com/vmalert.html .
` `
flagutil.Usage(s) flagutil.Usage(s)
} }
func configReload(ctx context.Context, m *manager, groupsCfg []config.Group) {
// Register SIGHUP handler for config re-read just before manager.start call.
// This guarantees that the config will be re-read if the signal arrives during manager.start call.
// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1240
sighupCh := procutil.NewSighupChan()
var configCheckCh <-chan time.Time
if *rulesCheckInterval > 0 {
ticker := time.NewTicker(*rulesCheckInterval)
configCheckCh = ticker.C
defer ticker.Stop()
}
// init reload metrics with positive values to improve alerting conditions
configSuccess.Set(1)
configTimestamp.Set(fasttime.UnixTimestamp())
for {
select {
case <-ctx.Done():
return
case <-sighupCh:
logger.Infof("SIGHUP received. Going to reload rules %q ...", *rulePath)
configReloads.Inc()
case <-configCheckCh:
}
newGroupsCfg, err := config.Parse(*rulePath, *validateTemplates, *validateExpressions)
if err != nil {
logger.Errorf("cannot parse configuration file: %s", err)
continue
}
if configsEqual(newGroupsCfg, groupsCfg) {
// config didn't change - skip it
continue
}
groupsCfg = newGroupsCfg
if err := m.update(ctx, groupsCfg, false); err != nil {
configReloadErrors.Inc()
configSuccess.Set(0)
logger.Errorf("error while reloading rules: %s", err)
continue
}
configSuccess.Set(1)
configTimestamp.Set(fasttime.UnixTimestamp())
logger.Infof("Rules reloaded successfully from %q", *rulePath)
}
}
func configsEqual(a, b []config.Group) bool {
if len(a) != len(b) {
return false
}
for i := range a {
if a[i].Checksum != b[i].Checksum {
return false
}
}
return true
}

96
app/vmalert/main_test.go
View file

@ -1,12 +1,16 @@
package main package main
import ( import (
"context"
"fmt" "fmt"
"io/ioutil"
"net/url" "net/url"
"os" "os"
"testing" "testing"
"time"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier" "github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/procutil"
) )
func TestGetExternalURL(t *testing.T) { func TestGetExternalURL(t *testing.T) {
@ -51,3 +55,95 @@ func TestGetAlertURLGenerator(t *testing.T) {
t.Errorf("unexpected url want %s, got %s", exp, fn(testAlert)) t.Errorf("unexpected url want %s, got %s", exp, fn(testAlert))
} }
} }
func TestConfigReload(t *testing.T) {
originalRulePath := *rulePath
defer func() {
*rulePath = originalRulePath
}()
const (
rules1 = `
groups:
- name: group-1
rules:
- alert: ExampleAlertAlwaysFiring
expr: sum by(job) (up == 1)
- record: handler:requests:rate5m
expr: sum(rate(prometheus_http_requests_total[5m])) by (handler)
`
rules2 = `
groups:
- name: group-1
rules:
- alert: ExampleAlertAlwaysFiring
expr: sum by(job) (up == 1)
- name: group-2
rules:
- record: handler:requests:rate5m
expr: sum(rate(prometheus_http_requests_total[5m])) by (handler)
`
)
f, err := ioutil.TempFile("", "")
if err != nil {
t.Fatal(err)
}
writeToFile(t, f.Name(), rules1)
*rulesCheckInterval = 200 * time.Millisecond
*rulePath = []string{f.Name()}
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
m := &manager{
querierBuilder: &fakeQuerier{},
groups: make(map[uint64]*Group),
labels: map[string]string{},
}
go configReload(ctx, m, nil)
lenLocked := func(m *manager) int {
m.groupsMu.RLock()
defer m.groupsMu.RUnlock()
return len(m.groups)
}
time.Sleep(*rulesCheckInterval * 2)
groupsLen := lenLocked(m)
if groupsLen != 1 {
t.Fatalf("expected to have exactly 1 group loaded; got %d", groupsLen)
}
writeToFile(t, f.Name(), rules2)
time.Sleep(*rulesCheckInterval * 2)
groupsLen = lenLocked(m)
if groupsLen != 2 {
fmt.Println(m.groups)
t.Fatalf("expected to have exactly 2 groups loaded; got %d", groupsLen)
}
writeToFile(t, f.Name(), rules1)
procutil.SelfSIGHUP()
time.Sleep(*rulesCheckInterval / 2)
groupsLen = lenLocked(m)
if groupsLen != 1 {
t.Fatalf("expected to have exactly 1 group loaded; got %d", groupsLen)
}
writeToFile(t, f.Name(), `corrupted`)
procutil.SelfSIGHUP()
time.Sleep(*rulesCheckInterval / 2)
groupsLen = lenLocked(m)
if groupsLen != 1 { // should remain unchanged
t.Fatalf("expected to have exactly 1 group loaded; got %d", groupsLen)
}
}
func writeToFile(t *testing.T, file, b string) {
t.Helper()
err := ioutil.WriteFile(file, []byte(b), 0644)
if err != nil {
t.Fatal(err)
}
}

13
app/vmalert/manager.go
View file

@ -3,7 +3,6 @@ package main
import ( import (
"context" "context"
"fmt" "fmt"
"strings"
"sync" "sync"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/config" "github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/config"
@ -50,8 +49,8 @@ func (m *manager) AlertAPI(gID, aID uint64) (*APIAlert, error) {
return nil, fmt.Errorf("can't find alert with id %q in group %q", aID, g.Name) return nil, fmt.Errorf("can't find alert with id %q in group %q", aID, g.Name)
} }
func (m *manager) start(ctx context.Context, path []string, validateTpl, validateExpr bool) error { func (m *manager) start(ctx context.Context, groupsCfg []config.Group) error {
return m.update(ctx, path, validateTpl, validateExpr, true) return m.update(ctx, groupsCfg, true)
} }
func (m *manager) close() { func (m *manager) close() {
@ -85,13 +84,7 @@ func (m *manager) startGroup(ctx context.Context, group *Group, restore bool) er
return nil return nil
} }
func (m *manager) update(ctx context.Context, path []string, validateTpl, validateExpr, restore bool) error { func (m *manager) update(ctx context.Context, groupsCfg []config.Group, restore bool) error {
logger.Infof("reading rules configuration file from %q", strings.Join(path, ";"))
groupsCfg, err := config.Parse(path, validateTpl, validateExpr)
if err != nil {
return fmt.Errorf("cannot parse configuration file: %w", err)
}
groupsRegistry := make(map[uint64]*Group) groupsRegistry := make(map[uint64]*Group)
for _, cfg := range groupsCfg { for _, cfg := range groupsCfg {
ng := newGroup(cfg, m.querierBuilder, *evaluationInterval, m.labels) ng := newGroup(cfg, m.querierBuilder, *evaluationInterval, m.labels)

37
app/vmalert/manager_test.go
View file

@ -9,8 +9,8 @@ import (
"testing" "testing"
"time" "time"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/config"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource" "github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier" "github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
) )
@ -25,9 +25,8 @@ func TestMain(m *testing.M) {
// starting with empty rules folder // starting with empty rules folder
func TestManagerEmptyRulesDir(t *testing.T) { func TestManagerEmptyRulesDir(t *testing.T) {
m := &manager{groups: make(map[uint64]*Group)} m := &manager{groups: make(map[uint64]*Group)}
path := []string{"foo/bar"} cfg := loadCfg(t, []string{"foo/bar"}, true, true)
err := m.update(context.Background(), path, true, true, false) if err := m.update(context.Background(), cfg, false); err != nil {
if err != nil {
t.Fatalf("expected to load succesfully with empty rules dir; got err instead: %v", err) t.Fatalf("expected to load succesfully with empty rules dir; got err instead: %v", err)
} }
} }
@ -51,7 +50,8 @@ func TestManagerUpdateConcurrent(t *testing.T) {
"config/testdata/rules2-good.rules", "config/testdata/rules2-good.rules",
} }
*evaluationInterval = time.Millisecond *evaluationInterval = time.Millisecond
if err := m.start(context.Background(), []string{paths[0]}, true, true); err != nil { cfg := loadCfg(t, []string{paths[0]}, true, true)
if err := m.start(context.Background(), cfg); err != nil {
t.Fatalf("failed to start: %s", err) t.Fatalf("failed to start: %s", err)
} }
@ -64,8 +64,11 @@ func TestManagerUpdateConcurrent(t *testing.T) {
defer wg.Done() defer wg.Done()
for i := 0; i < iterations; i++ { for i := 0; i < iterations; i++ {
rnd := rand.Intn(len(paths)) rnd := rand.Intn(len(paths))
path := []string{paths[rnd]} cfg, err := config.Parse([]string{paths[rnd]}, true, true)
_ = m.update(context.Background(), path, true, true, false) if err != nil { // update can fail and this is expected
continue
}
_ = m.update(context.Background(), cfg, false)
} }
}() }()
} }
@ -243,13 +246,16 @@ func TestManagerUpdate(t *testing.T) {
t.Run(tc.name, func(t *testing.T) { t.Run(tc.name, func(t *testing.T) {
ctx, cancel := context.WithCancel(context.TODO()) ctx, cancel := context.WithCancel(context.TODO())
m := &manager{groups: make(map[uint64]*Group), querierBuilder: &fakeQuerier{}} m := &manager{groups: make(map[uint64]*Group), querierBuilder: &fakeQuerier{}}
path := []string{tc.initPath}
if err := m.update(ctx, path, true, true, false); err != nil { cfgInit := loadCfg(t, []string{tc.initPath}, true, true)
if err := m.update(ctx, cfgInit, false); err != nil {
t.Fatalf("failed to complete initial rules update: %s", err) t.Fatalf("failed to complete initial rules update: %s", err)
} }
path = []string{tc.updatePath} cfgUpdate, err := config.Parse([]string{tc.updatePath}, true, true)
_ = m.update(ctx, path, true, true, false) if err == nil { // update can fail and that's expected
_ = m.update(ctx, cfgUpdate, false)
}
if len(tc.want) != len(m.groups) { if len(tc.want) != len(m.groups) {
t.Fatalf("\nwant number of groups: %d;\ngot: %d ", len(tc.want), len(m.groups)) t.Fatalf("\nwant number of groups: %d;\ngot: %d ", len(tc.want), len(m.groups))
} }
@ -267,3 +273,12 @@ func TestManagerUpdate(t *testing.T) {
}) })
} }
} }
func loadCfg(t *testing.T, path []string, validateAnnotations, validateExpressions bool) []config.Group {
t.Helper()
cfg, err := config.Parse(path, validateAnnotations, validateExpressions)
if err != nil {
t.Fatal(err)
}
return cfg
}